$ loading_
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall" MCP 服务： 执行：claude mcp add --transport http 'dev-agentdiet-prompt-guard' 'https://prompt-guard.agentdiet.dev/mcp'
Strips 85-97% of HTML/DOM bloat into clean Markdown or JSON with cryptographic ROI proof.
Extracts verified emails, social links, 40+ tech stack signals, pricing tiers, and company summar.
Scans live DeFiLlama APYs, TVL depth, and risk-adjusted yield spreads across Base, Arbitrum, Sola.
Queries live HackerNews discussions, front-page velocity, and developer sentiment on any framewor.
Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes).
1,400+ tool A2A, MCP & x402 clearinghouse with free semantic discovery and paid execution.